Postprint version. Published in Journal of Safety Research, Volume 36, Issue 1, January 1, 2005, pages 97-108.
NOTE: At the time of publication, the author Anurag Pande was not yet affiliated with Cal Poly.
Introduction: In spite of recent advances in traffic surveillance technology and ever-growing concern over traffic safety, there have been very few research efforts establishing links between real-time traffic flow parameters and crash occurrence. This study aims at identifying patterns in the freeway loop detector data that potentially precede traffic crashes.
Method: The proposed solution essentially involves classification of traffic speed patterns emerging from the loop detector data. Historical crash and loop detector data from the Interstate-4 corridor in the Orlando metropolitan area were used for this study. Traffic speed data from sensors embedded in the pavement (i.e., loop detector stations) to measure characteristics of the traffic flow were collected for both crash and non-crash conditions. Bayesian classifier based methodology, probabilistic neural network (PNN), was then used to classify these data as belonging to either crashes or non-crashes. PNN is a neural network implementation of well-known Bayesian-Parzen classifier. With its superb mathematical credentials, the PNN trains much faster than multilayer feed forward networks. The inputs to final classification model, selected from various candidate models, were logarithms of the coefficient of variation in speed obtained from three stations, namely, station of the crash (i.e., station nearest to the crash location) and two stations immediately preceding it in the upstream direction (measured in 5 minute time slices of 10–15 minutes prior to the crash time).
Results: The results showed that at least 70% of the crashes on the evaluation dataset could be identified using the classifiers developed in this paper.
Civil and Environmental Engineering